tiny-mlm-glue-wnli-from-scratch-custom-tokenizer-expand-vocab – AI Model by muhtasham | AlphaNeural AI

You can deploy this model and start earning money today!

muhtasham/
tiny-mlm-glue-wnli-from-scratch-custom-tokenizer-expand-vocab

like

0

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

tiny-mlm-glue-wnli-from-scratch-custom-tokenizer-expand-vocab

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 5.5263

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss
9.1486	6.25	500	7.8470
7.1116	12.5	1000	6.6165
6.3036	18.75	1500	6.1976
6.0919	25.0	2000	6.2290
6.0014	31.25	2500	6.0136
5.9682	37.5	3000	5.8730
5.8571	43.75	3500	5.7612
5.8144	50.0	4000	5.7921
5.7654	56.25	4500	5.8279
5.7322	62.5	5000	5.5263

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.13.1+cu116
Datasets 2.9.1.dev0
Tokenizers 0.13.2